CN108319917A - Key message Enhancement Method, apparatus and system, storage medium in certificate image - Google Patents
Key message Enhancement Method, apparatus and system, storage medium in certificate image Download PDFInfo
- Publication number
- CN108319917A CN108319917A CN201810104852.3A CN201810104852A CN108319917A CN 108319917 A CN108319917 A CN 108319917A CN 201810104852 A CN201810104852 A CN 201810104852A CN 108319917 A CN108319917 A CN 108319917A
- Authority
- CN
- China
- Prior art keywords
- certificate
- image
- certificate image
- key message
- fuzzy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
Abstract
The present invention provides key message Enhancement Method, apparatus and system, storage medium in a kind of certificate image, wherein method includes：Certificate type is determined according to fuzzy certificate image；The clear certificate image of same type is transferred from far-end server according to the certificate type；Extract the partitioning scheme of the clear certificate image；Fuzzy certificate image is split using the partitioning scheme to obtain segmentation certificate image；Key message enhancing is carried out to the segmentation certificate image to handle to obtain certificate enhancing image.The present invention can improve the accuracy of OCR character recognition technologies pointedly to obscuring partial information or key message progress image enhancement processing in certificate image.
Description
Technical field
The present invention relates to technical field of image processing more particularly to image information Enhancement Methods, are exactly specifically a kind of
Key message Enhancement Method, apparatus and system, storage medium in certificate image.
Background technology
Increasingly dependence with people to computer technology and network communication needs to calculate a large amount of papery data typing
Machine is scanned certificate, material, qualifications for example, during movable property and real estate sales/purchase, lease, to historical document,
Books carry out electronic disposal.In order to preferably preserve, retrieve, check that word class paper material, people develop word knowledge again
Other technology, the text information in automatic identification picture or photo.
So-called Text region is exactly the technology using Computer Automatic Recognition character, is a weight of application of pattern recognition
Want field.The last century 50's people start to inquire into normal words recognition methods, and develop optical character recognition reader；60 years
There is the practical machine using magnetic ink and sytlized font for initial stage, multiple fonts and hand-written occurs in the later stage sixties
Body Text region machine, accuracy of identification and machine performance all can substantially be met the requirements, for example, the handwritten form for letter sorting
Digital cognitron and block letter English digital cognitron；The basic theories of the main study text identification of the people seventies and development are high
The Text region machine of performance, and focus on the research of Chinese Character Recognition.Wherein, OCR (optical
Characterrecognition) Text region is the representative of character recognition technology.
OCR technique refers to that electronic equipment (for example, scanner or digital camera) checks the character printed on paper, then uses word
Shape is translated into the process of computword by symbol recognition methods；That is, be scanned to text information, then to image file into
Row analyzing processing obtains the process of word and layout information.OCR technique is able to extensive use in production and living, Chinese
It is the features such as discrimination of block letter can reach 98% or more, the friendly of OCR technique, stability, ease for use and feasibility, deep
By Text region, worker is liked.
Current OCR technique can accurately handle the high-definition image (figure obtained from scanner obtained from scanner
Picture obtains under the conditions of source document is entirely clear, therefore hardly there is geometric distortion), for visually depositing
In centainly fuzzy image, existing OCR technique can barely cope with, but be frequently present of identification deviation or identify asking for mistake
Topic, main reason is that OCR technique cannot efficiently use binaryzation method carries out feature extraction to certificate image.Such as diploma,
The certificates such as business license, since the time is remote, it is improper to preserve, and many key messages start to obscure, and Text region often goes out
Existing deviation, needs manually to proofread, and increases human cost；In addition, above these certificate images other than with text information, also
With non-legible information such as a large amount of mark, pictures, if using these fuzzy marks of OCR technique Direct Recognition, can incite somebody to action often
These fuzzy marks are identified as word.
Therefore, those skilled in the art are there is an urgent need for researching and developing a kind of certificate image key message Enhancement Method, to fuzzy card
Book image precisely identifies.
Invention content
In view of this, the technical problem to be solved in the present invention is to provide key message enhancing side in a kind of certificate image
Method, apparatus and system, storage medium solve the problems, such as that existing OCR technique can not correctly identify fuzzy certificate image.
In order to solve the above-mentioned technical problem, key message increases in a kind of certificate image of specific implementation mode of the invention offer
Strong method, including：Certificate type is determined according to fuzzy certificate image；It is transferred from far-end server according to the certificate type identical
The clear certificate image of type；Extract the partitioning scheme of the clear certificate image；Using the partitioning scheme to obscuring certificate
Image is split to obtain segmentation certificate image；Key message enhancing is carried out to the segmentation certificate image to handle to obtain certificate increasing
Strong image.
The specific implementation mode of the present invention also provides key message intensifier in a kind of certificate image, including：It determines single
Member, for determining certificate type according to fuzzy certificate image；Transfer unit, for according to the certificate type from far-end server
Transfer the clear certificate image of same type；Extraction unit, the partitioning scheme for extracting the clear certificate image；Segmentation is single
Member obtains segmentation certificate image for being split to fuzzy certificate image using the partitioning scheme；Enhancement unit, for pair
The segmentation certificate image carries out key message enhancing and handles to obtain certificate enhancing image.
The specific implementation mode of the present invention also provides key message enhancing system in a kind of certificate image, including：Multiple passes
Key information intensifier, and the far-end server that is connect with the key message intensifier.Wherein, the key message increases
Intensity device is used to determine certificate type according to the fuzzy certificate image；The far-end server is used for according to the fuzzy certificate
The clear certificate image that the certificate type of image is provided to the key message intensifier；The key message enhancing dress
The partitioning scheme enhancing for setting the clear certificate image for being additionally operable to provide with reference to the far-end server obscures certificate image.
The specific implementation mode of the present invention also provides a kind of computer storage media including computer executed instructions, described
When computer executed instructions are handled via data processing equipment, which executes certificate image key message identification side
Method.
Above-mentioned specific implementation mode according to the present invention it is found that key message Enhancement Method, device and be in certificate image
System, storage medium at least have the advantages that：The type for determining certificate according to fuzzy certificate image first, further according to certificate
Type the clear certificate image of same type is transferred from far-end server, then the clear certificate image transferred is identified
Segmentation is split fuzzy certificate image referring again to the partitioning scheme of clear certificate image, then to the fuzzy card after segmentation
Book image carries out image enhancement processing, finally identification enhancing treated fuzzy certificate image.The present invention can be pointedly right
Partial information or key message in fuzzy certificate image carry out image enhancement processing, pointedly reject due to certificate is antiquated,
The picture noise caused by reasons such as fold to interfere, it is accurate to restore to obscure the key message in certificate image, can effectively reduce by
The OCR image recognition mistakes caused by image is fuzzy, improve the accuracy of OCR character recognition technologies.
It is to be understood that above-mentioned general description and detailed description below are merely illustrative and illustrative, not
It can the limitation range of the invention to be advocated.
Description of the drawings
Following appended attached drawing is the part of specification of the present invention, depicts example embodiments of the present invention, institute
Attached drawing is used for illustrating the principle of the present invention together with the description of specification.
Fig. 1 is the embodiment one of key message Enhancement Method in a kind of certificate image that the specific embodiment of the invention provides
Flow chart.
Fig. 2 is the embodiment two of key message Enhancement Method in a kind of certificate image that the specific embodiment of the invention provides
Flow chart.
Fig. 3 is the embodiment three of key message Enhancement Method in a kind of certificate image that the specific embodiment of the invention provides
Flow chart.
Fig. 4 is the example IV of key message Enhancement Method in a kind of certificate image that the specific embodiment of the invention provides
Flow chart.
Fig. 5 is the embodiment one of key message intensifier in a kind of certificate image that the specific embodiment of the invention provides
Structural schematic diagram.
Fig. 6 is the embodiment two of key message intensifier in a kind of certificate image that the specific embodiment of the invention provides
Structural schematic diagram.
Fig. 7 is the embodiment three of key message intensifier in a kind of certificate image that the specific embodiment of the invention provides
Structural schematic diagram.
Fig. 8 is the example IV of key message intensifier in a kind of certificate image that the specific embodiment of the invention provides
Structural schematic diagram.
Fig. 9 is that key message enhances systematic difference signal in a kind of certificate image that the specific embodiment of the invention provides
Figure.
Specific implementation mode
Understand in order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below will with attached drawing and in detail
Narration clearly illustrates that the spirit of disclosed content, any skilled artisan are understanding the content of present invention
After embodiment, when the technology that can be taught by the content of present invention, it is changed and modifies, without departing from the essence of the content of present invention
God and range.
The illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but not as a limitation of the invention.
In addition, in the drawings and embodiments the use of element/component of same or like label is for representing same or like portion
Point.
About " first " used herein, " second " ... etc., not especially censure the meaning of order or cis-position,
It is non-to limit the present invention, only for distinguishing the element described with same technique term or operation.
About direction term used herein, such as：Upper and lower, left and right, front or rear etc. are only the sides of refer to the attached drawing
To.Therefore, the direction term used is intended to be illustrative and not intended to limit this creation.
It is the term of opening, i.e., about "comprising" used herein, " comprising ", " having ", " containing " etc.
Mean including but not limited to.
About it is used herein " and/or ", include the things any or all combinations.
Include " two " and " two or more " about " multiple " herein；Include " two groups " about " multigroup " herein
And " more than two ".
About term used herein " substantially ", " about " etc., to modify it is any can be with the quantity or mistake of microvariations
Difference, but this slight variations or error can't change its essence.In general, microvariations that such term is modified or error
Range in some embodiments can be 20%, in some embodiments can be 10%, can be in some embodiments 5% or its
His numerical value.It will be understood by those skilled in the art that the aforementioned numerical value referred to can be adjusted according to actual demand, it is not limited thereto.
It is certain describing the word of the application by lower or discuss in the other places of this specification, to provide art technology
Personnel's guiding additional in relation to the description of the present application.
Fig. 1 is the embodiment one of key message Enhancement Method in a kind of certificate image that the specific embodiment of the invention provides
Flow chart, as shown in Figure 1, the clear card of same type is transferred from far-end server according to the certificate type of fuzzy certificate image
Book image, then the partitioning scheme of clear certificate image is extracted, then fuzzy certificate image is split using partitioning scheme
To segmentation certificate image, key message enhancing processing finally is carried out to segmentation certificate image.
In the specific implementation mode shown in the drawings, key message Enhancement Method includes in certificate image：
Step 101：Certificate type is determined according to fuzzy certificate image.In specific embodiments of the present invention, certificate graphs are obscured
As referring specifically to the unsharp certificate image of partial information, these certificates cause certification portions due to shabby, folding, colour fading etc.
Information is unintelligible；Certificate type includes identity card, diploma, marriage certificate, honorary certificate, business license etc..
Step 102：The clear certificate image of same type is transferred from far-end server according to the certificate type.The present invention
Specific embodiment in, far-end server can be Cloud Server, integrating server etc.；Clear certificate image is far-end server
Storage, and type certificate image identical with fuzzy certificate image.
Step 103：Extract the partitioning scheme of the clear certificate image.In specific embodiments of the present invention, according to clear
The text information of certificate image sets Text segmentation table, and determines partitioning scheme according to Text segmentation table.
Step 104：Fuzzy certificate image is split using the partitioning scheme to obtain segmentation certificate image.The present invention
Specific embodiment in, divided according to the partitioning scheme of clear certificate image and obscure certificate image, extracted and obscure in certificate image
Text information, the text information image of extraction is to divide certificate image.
Step 105：Key message enhancing is carried out to the segmentation certificate image to handle to obtain certificate enhancing image.The present invention
Specific embodiment in, filter out segmentation certificate image in interference, noise, allow certificate enhancing image meet OCR Text regions
It is required that.
Referring to Fig. 1, the present invention pointedly can carry out figure to obscuring partial information in certificate image or key message
Image intensifying is handled, and is pointedly rejected picture noise caused by due to certificate is antiquated, folds, fades etc. and is interfered, accurate extensive
The key message in certificate image is obscured again, can effectively reduce the OCR image recognition mistakes caused by image is fuzzy.
Fig. 2 is the embodiment two of key message Enhancement Method in a kind of certificate image that the specific embodiment of the invention provides
Flow chart, as shown in Fig. 2, to segmentation certificate image after key message enhancing handles to obtain certificate enhancing image, know
Other certificate enhances image.
In the specific implementation mode shown in the drawings, after step 105, key message Enhancement Method is also wrapped in certificate image
It includes：
Step 106：Identify that the certificate enhancing image obtains editable digital certificate image.Specific embodiments of the present invention
In, the behaviour such as the text information in editable digital certificate image specific number certificate image can modify, delete, editing
Make.
Referring to Fig. 2, enhances image using OCR character recognition technologies identification certificate, obtain the digital certificate figure that can be edited
Picture facilitates user to carry out relevant operation.
Fig. 3 is the embodiment three of key message Enhancement Method in a kind of certificate image that the specific embodiment of the invention provides
Flow chart, as shown in figure 3, determining certificate type according to the main feature of fuzzy certificate image.
In the specific implementation mode shown in the drawings, step 101 specifically includes：
Step 1011：Extract the main feature of the fuzzy certificate image.In specific embodiments of the present invention, certificate is obscured
Image is that partial information is unintelligible, and partial information is still clear, for example, for marriage certificate, usual " marriage certificate " three
Big word is due to being original print body, and fugitive color, certificate type is not determined by " marriage certificate " three big word and man and wife's photo
For marriage certificate, then by information such as national emblem, font size, picture locations, determine the version of marriage certificate.
Step 1012：The certificate type is determined according to the main feature.It is main special in specific embodiments of the present invention
Sign refers mainly in certificate not fugitive color or is not easy the information such as fuzzy word, image, figure, for example, " the graduation in diploma
Three big words of card ", the original prints information such as photographic intelligence.
Referring to Fig. 3, according to main feature (the not letters such as fugitive color or fuzzy word, image, figure of fuzzy certificate image
Breath) determine certificate type, the certificate type of paste certificate image can be precisely locked, to pointedly carry out at image enhancement
Reason improves the accuracy of OCR Text regions.
Fig. 4 is the example IV of key message Enhancement Method in a kind of certificate image that the specific embodiment of the invention provides
Flow chart, as shown in figure 4, extract the partitioning scheme of clear certificate image, to utilize the partitioning scheme of clear certificate image
Fuzzy certificate image is split.
In the specific implementation mode shown in the drawings, step 103 specifically includes：
Step 1031：Extract the text information of the clear certificate image.In specific embodiments of the present invention, pass through OCR
The modes such as character recognition technology extract the text information of clear certificate image.
Step 1032：Text segmentation table is set according to the text information.In specific embodiments of the present invention, Text segmentation
Table refers specifically to the table of delineation text information, wherein there are one font (number, Chinese character or words etc.) in each cell.
Step 1033：The partitioning scheme is determined according to the Text segmentation table.
Referring to Fig. 4, the partitioning scheme of clear certificate image is extracted, is divided using the partitioning scheme of clear certificate image similar
The fuzzy certificate image of type can effectively divide fuzzy certificate image, and later image enhancing can be accomplished to shoot the arrow at the target,
To improve the precision of OCR character recognition technologies.
Fig. 5 is the embodiment one of key message intensifier in a kind of certificate image that the specific embodiment of the invention provides
Structural schematic diagram, device as shown in Figure 5 can be applied in Fig. 1~method shown in Fig. 4, according to fuzzy certificate image
Certificate type transfers the clear certificate image of same type from far-end server, then extracts the partitioning scheme of clear certificate image,
Then fuzzy certificate image is split using partitioning scheme to obtain segmentation certificate image, finally segmentation certificate image is carried out
Key message enhancing is handled.
In the specific implementation mode shown in the drawings, key message intensifier includes in certificate image：Determination unit 1,
Transfer unit 2, extraction unit 3, cutting unit 4 and enhancement unit 5.Wherein it is determined that unit 1 is for true according to certificate image is obscured
Determine certificate type；Transfer clear certificate graphs of the unit 2 for transferring same type from far-end server according to the certificate type
Picture；Extraction unit 3 is used to extract the partitioning scheme of the clear certificate image；Cutting unit 4 is used to utilize the partitioning scheme
Fuzzy certificate image is split to obtain segmentation certificate image；Enhancement unit 5 is for closing the segmentation certificate image
Key information enhancing handles to obtain certificate enhancing image.
Referring to Fig. 5, the present invention pointedly can carry out figure to obscuring partial information in certificate image or key message
Image intensifying is handled, and is pointedly rejected picture noise caused by due to certificate is antiquated, folds, fades etc. and is interfered, accurate extensive
The key message in certificate image is obscured again, can effectively reduce the OCR image recognition mistakes caused by image is fuzzy.
Fig. 6 is the embodiment two of key message intensifier in a kind of certificate image that the specific embodiment of the invention provides
Structural schematic diagram, as shown in fig. 6, to segmentation certificate image carry out key message enhancing handle to obtain certificate enhancing image it
Afterwards, recognition unit identification certificate enhances image.
In the specific implementation mode shown in the drawings, key message intensifier further includes recognition unit 6 in certificate image.
Wherein, the certificate enhancing image obtains editable digital certificate image to recognition unit 6 for identification.
Referring to Fig. 2, enhances image using OCR character recognition technologies identification certificate, obtain the digital certificate figure that can be edited
Picture facilitates user to carry out relevant operation.
Fig. 7 is the embodiment three of key message intensifier in a kind of certificate image that the specific embodiment of the invention provides
Structural schematic diagram, as shown in fig. 7, determination unit determines certificate type according to the main feature of fuzzy certificate image.
In the specific implementation mode shown in the drawings, the determination unit 1 specifically includes：Extraction module 11 and determining module
12.Wherein, extraction module 11 is used to extract the main feature of the fuzzy certificate image；Determining module 12 is used for according to the master
Feature is wanted to determine the certificate type.
Referring to Fig. 7, according to main feature (the not letters such as fugitive color or fuzzy word, image, figure of fuzzy certificate image
Breath) determine certificate type, the certificate type of paste certificate image can be precisely locked, to pointedly carry out at image enhancement
Reason improves the accuracy of OCR Text regions.
Fig. 8 is the example IV of key message intensifier in a kind of certificate image that the specific embodiment of the invention provides
Structural schematic diagram, as shown in figure 8, extract the partitioning scheme of clear certificate image, to utilize the segmentation of clear certificate image
Mode is split fuzzy certificate image.
In the specific implementation mode shown in the drawings, the extraction unit 3 specifically includes：Extraction module 31, setting module
32 and determining module 33.Wherein, extraction module 31 is used to extract the text information of the clear certificate image；Setting module 32 is used
According to text information setting Text segmentation table；Determining module 33 is used to determine the segmentation according to the Text segmentation table
Mode.
Referring to Fig. 8, the partitioning scheme of clear certificate image is extracted, is divided using the partitioning scheme of clear certificate image similar
The fuzzy certificate image of type can effectively divide fuzzy certificate image, and later image enhancing can be accomplished to shoot the arrow at the target,
To improve the precision of OCR character recognition technologies.
Fig. 9 is that key message enhances systematic difference signal in a kind of certificate image that the specific embodiment of the invention provides
Figure, as shown in figure 9, a far-end server is connect with multiple key message intensifiers, key message intensifier is according to mould
Paste certificate image determines certificate type, and the certificate type that far-end server is provided according to key message intensifier is to key message
Intensifier provides clear certificate image, and key message intensifier analyzes the partitioning scheme of clear certificate image, and using clearly
The partitioning scheme segmentation of clear certificate image obscures certificate image.
In the specific implementation mode shown in the drawings, key message enhancing system includes in certificate image：Multiple crucial letters
Intensifier 100 is ceased, and the far-end server 200 being connect with the key message intensifier 100.Wherein, the key
Information enhancement device 100 is used to determine certificate type according to the fuzzy certificate image；The far-end server 200 is used for basis
The clear certificate image that the certificate type of the fuzzy certificate image is provided to the key message intensifier 100；Institute
State the partitioning scheme that key message intensifier 100 is additionally operable to the clear certificate image provided with reference to the far-end server 200
Enhancing obscures certificate image.
Further, key message intensifier 100 includes：Determination unit 1 transfers unit 2, extraction unit 3, segmentation list
Member 4, enhancement unit 5 and recognition unit 6.Wherein it is determined that unit 1 is used to determine certificate type according to fuzzy certificate image；It transfers
Unit 2 is used to transfer the clear certificate image of same type from far-end server 200 according to the certificate type；Extraction unit 3
Partitioning scheme for extracting the clear certificate image；Cutting unit 4 is used for using the partitioning scheme to obscuring certificate graphs
As being split to obtain segmentation certificate image；Enhancement unit 5 is used to carry out at key message enhancing the segmentation certificate image
Reason obtains certificate enhancing image；The certificate enhancing image obtains editable digital certificate image to recognition unit 6 for identification.Example
Such as, certain diploma is due to of the remote past, and upper part word type information is faded, and determination unit 1 is according to fuzzy certificate graphs
As determining that certificate type is the card that passes through college of certain colleges and universities；Transfer unit 2 from far-end server 200 transfer the colleges and universities undergraduate course finish
The clear certificate image of industry card；Extraction unit 3 extracts the partitioning scheme of the clear certificate image for the card that passes through college；Cutting unit 4
Fuzzy certificate image is split using above-mentioned partitioning scheme, so as to enhancement unit 5 pointedly to fuzzy certificate image into
Row image enhancement processing；Recognition unit 6 can accurately identify certificate enhancing image, be less prone to identification error or mistake.
It, can be pointedly to obscuring partial information or key message progress image enhancement in certificate image referring to Fig. 9
Processing is pointedly rejected picture noise caused by due to certificate is antiquated, folds etc. and is interfered, accurate to restore to obscure certificate graphs
Key message as in can effectively reduce the OCR image recognition mistakes caused by image is fuzzy, improve OCR Text regions
The accuracy of technology.
The specific embodiment of the invention provides a kind of computer storage media including computer executed instructions, the computer
It executes instruction when being handled via data processing equipment, which executes certificate image key message recognition methods.Side
Method includes the following steps：
Step 101：Certificate type is determined according to fuzzy certificate image.
Step 102：The clear certificate image of same type is transferred from far-end server according to the certificate type.
Step 103：Extract the partitioning scheme of the clear certificate image.
Step 104：Fuzzy certificate image is split using the partitioning scheme to obtain segmentation certificate image.
Step 105：Key message enhancing is carried out to the segmentation certificate image to handle to obtain certificate enhancing image.
The specific embodiment of the invention also provides a kind of computer storage media including computer executed instructions, the calculating
Machine executes instruction when being handled via data processing equipment, which executes certificate image key message recognition methods.
Method includes the following steps：
Step 101：Certificate type is determined according to fuzzy certificate image.
Step 102：The clear certificate image of same type is transferred from far-end server according to the certificate type.
Step 103：Extract the partitioning scheme of the clear certificate image.
Step 104：Fuzzy certificate image is split using the partitioning scheme to obtain segmentation certificate image.
Step 105：Key message enhancing is carried out to the segmentation certificate image to handle to obtain certificate enhancing image.
Step 106：Identify that the certificate enhancing image obtains editable digital certificate image.
The specific embodiment of the invention also provides a kind of computer storage media including computer executed instructions, the calculating
Machine executes instruction when being handled via data processing equipment, which executes certificate image key message recognition methods.
Method includes the following steps：
Step 1011：Extract the main feature of the fuzzy certificate image.
Step 1012：The certificate type is determined according to the main feature.
Step 102：The clear certificate image of same type is transferred from far-end server according to the certificate type.
Step 103：Extract the partitioning scheme of the clear certificate image.
Step 104：Fuzzy certificate image is split using the partitioning scheme to obtain segmentation certificate image.
Step 105：Key message enhancing is carried out to the segmentation certificate image to handle to obtain certificate enhancing image.
The specific embodiment of the invention also provides a kind of computer storage media including computer executed instructions, the calculating
Machine executes instruction when being handled via data processing equipment, which executes certificate image key message recognition methods.
Method includes the following steps：
Step 101：Certificate type is determined according to fuzzy certificate image.
Step 102：The clear certificate image of same type is transferred from far-end server according to the certificate type.
Step 1031：Extract the text information of the clear certificate image.
Step 1032：Text segmentation table is set according to the text information.
Step 1033：The partitioning scheme is determined according to the Text segmentation table.
Step 104：Fuzzy certificate image is split using the partitioning scheme to obtain segmentation certificate image.
Step 105：Key message enhancing is carried out to the segmentation certificate image to handle to obtain certificate enhancing image.
Key message Enhancement Method, apparatus and system, storage are situated between in a kind of certificate image of specific embodiment of the invention offer
Matter first determines the type of certificate according to fuzzy certificate image, same type is transferred from far-end server further according to the type of certificate
Clear certificate image, segmentation then is identified to the clear certificate image transferred, referring again to the segmentation of clear certificate image
Mode is split fuzzy certificate image, then carries out image enhancement processing to the fuzzy certificate image after segmentation, finally knows
It Zeng Qiang not treated fuzzy certificate image.The present invention can be pointedly to obscuring partial information or key in certificate image
Information carries out image enhancement processing, pointedly rejects picture noise caused by due to certificate is antiquated, folds etc. and interferes, accurate
Really restore to obscure the key message in certificate image, the OCR image recognition mistakes caused by image is fuzzy can be effectively reduced,
Improve the accuracy of OCR character recognition technologies.
The above-mentioned embodiment of the present invention can be implemented in various hardware, Software Coding or both combination.For example, this hair
Bright embodiment, which is alternatively in data signal processor (Digital Signal Processor, DSP), executes the above method
Program code.The present invention can also refer to computer processor, digital signal processor, microprocessor or field-programmable gate array
Arrange the multiple functions that (Field Programmable Gate Array, FPGA) is executed.Above-mentioned processing can be configured according to the present invention
Device executes particular task, and machine-readable software code or the firmware generation of the ad hoc approach that the present invention discloses are defined by executing
Code is completed.Software code or firmware code can be developed into different program languages and different formats or form.Or
Different target platform composing software codes.However, configuring generation according to the software code of execution task of the present invention and other types
Different code pattern, type and the language of code do not depart from spirit and scope of the invention.
The foregoing is merely the schematical specific implementation modes of the present invention, before the design and principle for not departing from the present invention
It puts, the equivalent variations and modification that any those skilled in the art is made should all belong to the scope of protection of the invention.
Claims (10)
1. key message Enhancement Method in a kind of certificate image, which is characterized in that this method includes：
Certificate type is determined according to fuzzy certificate image；
The clear certificate image of same type is transferred from far-end server according to the certificate type；
Extract the partitioning scheme of the clear certificate image；
Fuzzy certificate image is split using the partitioning scheme to obtain segmentation certificate image；And
Key message enhancing is carried out to the segmentation certificate image to handle to obtain certificate enhancing image.
2. key message Enhancement Method in certificate image as described in claim 1, which is characterized in that the segmentation certificate graphs
After carrying out the step of key message enhancing handles to obtain certificate enhancing image, this method further includes：
Identify that the certificate enhancing image obtains editable digital certificate image.
3. key message Enhancement Method in certificate image as described in claim 1, which is characterized in that according to fuzzy certificate image
The step of determining certificate type specifically includes：
Extract the main feature of the fuzzy certificate image；And
The certificate type is determined according to the main feature.
4. key message Enhancement Method in certificate image as described in claim 1, which is characterized in that the extraction clear certificate
It the step of partitioning scheme of image, specifically includes：
Extract the text information of the clear certificate image；
Text segmentation table is set according to the text information；And
The partitioning scheme is determined according to the Text segmentation table.
5. key message intensifier in a kind of certificate image, which is characterized in that the device includes：
Determination unit, for determining certificate type according to fuzzy certificate image；
Unit is transferred, the clear certificate image for transferring same type from far-end server according to the certificate type；
Extraction unit, the partitioning scheme for extracting the clear certificate image；
Cutting unit obtains segmentation certificate image for being split to fuzzy certificate image using the partitioning scheme；And
Enhancement unit handles to obtain certificate enhancing image for carrying out key message enhancing to the segmentation certificate image.
6. key message intensifier in certificate image as claimed in claim 5, which is characterized in that the device further includes：
Recognition unit, for identification certificate enhancing image obtain editable digital certificate image.
7. key message intensifier in certificate image as claimed in claim 5, which is characterized in that the determination unit is specific
Including：
Extraction module, the main feature for extracting the fuzzy certificate image；And
Determining module, for determining the certificate type according to the main feature.
8. key message intensifier in certificate image as claimed in claim 5, which is characterized in that the extraction unit is specific
Including：
Extraction module, the text information for extracting the clear certificate image；
Setting module, for setting Text segmentation table according to the text information；And
Determining module, for determining the partitioning scheme according to the Text segmentation table.
9. key message enhances system in a kind of certificate image, which is characterized in that the system includes：Multiple such as claims 5~8
Any key message intensifier, and the far-end server that is connect with the key message intensifier, wherein
The key message intensifier is used to determine certificate type according to the fuzzy certificate image；
The far-end server is used to be enhanced to the key message according to the certificate type of the fuzzy certificate image and fill
The clear certificate image of offer is provided；
The key message intensifier is additionally operable to the partitioning scheme of the clear certificate image provided with reference to the far-end server
Enhancing obscures certificate image.
10. a kind of computer storage media including computer executed instructions, the computer executed instructions are via data processing
When equipment processing, which requires 1~4 any certificate image key message recognition methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810104852.3A CN108319917A (en) | 2018-02-02 | 2018-02-02 | Key message Enhancement Method, apparatus and system, storage medium in certificate image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810104852.3A CN108319917A (en) | 2018-02-02 | 2018-02-02 | Key message Enhancement Method, apparatus and system, storage medium in certificate image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108319917A true CN108319917A (en) | 2018-07-24 |
Family
ID=62891539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810104852.3A Pending CN108319917A (en) | 2018-02-02 | 2018-02-02 | Key message Enhancement Method, apparatus and system, storage medium in certificate image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108319917A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117115799A (en) * | 2023-09-11 | 2023-11-24 | 广州市西克传感器有限公司 | Tire character recognition method based on laser line scanning 3D camera |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236782A (en) * | 2010-04-30 | 2011-11-09 | 陈斌 | Character identification method for certificates |
| CN102402684A (en) * | 2010-09-15 | 2012-04-04 | 富士通株式会社 | Method and device for determining type of certificate and method and device for translating certificate |
| CN103208004A (en) * | 2013-03-15 | 2013-07-17 | 北京英迈杰科技有限公司 | Automatic recognition and extraction method and device for bill information area |
| CN103593642A (en) * | 2012-08-16 | 2014-02-19 | 阿里巴巴集团控股有限公司 | Card-information acquisition method and system |
| US20140072224A1 (en) * | 2010-03-11 | 2014-03-13 | Microsoft Corporation | Page layout determination of an image undergoing optical character recognition |
| CN104079587A (en) * | 2014-07-21 | 2014-10-01 | 深圳天祥质量技术服务有限公司 | Certificate identification device and certificate check system |
| CN107480670A (en) * | 2016-06-08 | 2017-12-15 | 北京新岸线网络技术有限公司 | A kind of method and apparatus of caption extraction |
| CN107480741A (en) * | 2017-09-08 | 2017-12-15 | 武汉市公安局出入境管理局 | A kind of portable quick identity scanning recognition instrument and its recognition methods |
-
2018
- 2018-02-02 CN CN201810104852.3A patent/CN108319917A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140072224A1 (en) * | 2010-03-11 | 2014-03-13 | Microsoft Corporation | Page layout determination of an image undergoing optical character recognition |
| CN102236782A (en) * | 2010-04-30 | 2011-11-09 | 陈斌 | Character identification method for certificates |
| CN102402684A (en) * | 2010-09-15 | 2012-04-04 | 富士通株式会社 | Method and device for determining type of certificate and method and device for translating certificate |
| CN103593642A (en) * | 2012-08-16 | 2014-02-19 | 阿里巴巴集团控股有限公司 | Card-information acquisition method and system |
| CN103208004A (en) * | 2013-03-15 | 2013-07-17 | 北京英迈杰科技有限公司 | Automatic recognition and extraction method and device for bill information area |
| CN104079587A (en) * | 2014-07-21 | 2014-10-01 | 深圳天祥质量技术服务有限公司 | Certificate identification device and certificate check system |
| CN107480670A (en) * | 2016-06-08 | 2017-12-15 | 北京新岸线网络技术有限公司 | A kind of method and apparatus of caption extraction |
| CN107480741A (en) * | 2017-09-08 | 2017-12-15 | 武汉市公安局出入境管理局 | A kind of portable quick identity scanning recognition instrument and its recognition methods |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117115799A (en) * | 2023-09-11 | 2023-11-24 | 广州市西克传感器有限公司 | Tire character recognition method based on laser line scanning 3D camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8494273B2 (en) | Adaptive optical character recognition on a document with distorted characters | |
| CN109948510B (en) | Document image instance segmentation method and device | |
| Chao et al. | Layout and content extraction for pdf documents | |
| CN110766014A (en) | Bill information positioning method, system and computer readable storage medium | |
| CN107944452A (en) | A kind of circular stamp character recognition method | |
| CN114299528B (en) | Information extraction and structuring method for scanned document | |
| JP5623079B2 (en) | Automatic generation of form definitions from hardcopy forms | |
| CN110442744A (en) | Extract method, apparatus, electronic equipment and the readable medium of target information in image | |
| CN108171239A (en) | The extracting method of certificate pictograph, apparatus and system, computer storage media | |
| US10528807B2 (en) | System and method for processing and identifying content in form documents | |
| CN112669515B (en) | Bill image recognition method and device, electronic equipment and storage medium | |
| CN109886257B (en) | Method for correcting invoice image segmentation result by adopting deep learning in OCR system | |
| JP4593729B2 (en) | A method of automatically recognizing text on a structured background by combining a background model and a character model | |
| Alomran et al. | Automated scoring system for multiple choice test with quick feedback | |
| CN104951749A (en) | Image content recognition device and image content recognition method | |
| CN112508000B (en) | Method and equipment for generating OCR image recognition model training data | |
| CN108319917A (en) | Key message Enhancement Method, apparatus and system, storage medium in certificate image | |
| CN111126273B (en) | Image processing method, device, electronic equipment and storage medium | |
| JP6035157B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| Dubey | Digital image restoration of historical devanagari manuscripts | |
| CN116758550A (en) | Text recognition method and device for form image, electronic equipment and storage medium | |
| Hidayatullah et al. | License plate detection and recognition for Indonesian cars | |
| CN108345895A (en) | Advertising image recognition methods and advertising image identifying system | |
| CN205563854U (en) | Serve all -in -one by oneself based on face detection and character recognition | |
| CN108734167B (en) | Method for recognizing characters on contaminated film |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180724 |